Watchlist tracking
Reviewed for relevance and future tracking value.
MCP100 Assessment
Watchlist / Tracking
Why we’re tracking it
Track client-version compatibility and the bridge's documented update path
Reviewed · Documentation review; complete setup workflow not independently tested
Best fit
Pairing ChatGPT planning/review with Codex coding execution through a read-only workspace bridge.
What we know
Codex with ChatGPT is a read-only MCP bridge that lets ChatGPT plan and review coding work while Codex performs execution in the workspace.
Maintenance / activity evidence
- Observed (UTC)docs: honor CODEX HOME in Codex paths ( 443)
Tracking evidence observed Oct 5, 2026. These dated signals do not establish current maintenance. Reviewed enrichment confidence: high.
Verification gaps / watch-outs
- Installation and comprehensive security have not been independently audited.
- Read-only workspace-bound access.
- OAuth 2.1 with PKCE S256 and one-time pairing code.
- Sensitive access: Selected source files; sensitive credential paths are denied by default
- The bridge is intentionally read-only and documents workspace scoping, sensitive-file denial and OAuth protection.
- No write/delete/shell/commit tools are exposed by design.
Full authority, access and evidence limits are available in Review context and Access & risk.
Popularity
7,070 repository stars
Stars observed Oct 6, 2026.
Do not use the unrelated npm package named c2c; its registry identity is different.
Do not use the unrelated npm package named c2c; its registry identity is different.
Do not use the unrelated npm package named c2c; its registry identity is different.
All limitations / Review context
Does the bridge still work with current ChatGPT and Codex client workflows?
The bounded assessment reviewed the official README, repository notices, security policy path, and security page for known material public-tracking blockers. No such blocker was identified. This is a public-tracking assessment, not an installation safety certification.
- The bridge is intentionally read-only and documents workspace scoping, sensitive-file denial and OAuth protection.
- No write/delete/shell/commit tools are exposed by design.
- Read-only workspace-bound access.
- OAuth 2.1 with PKCE S256 and one-time pairing code.
- Repository content stays in the workspace; the project documents default denial for sensitive files.
- Sensitive access: Selected source files; sensitive credential paths are denied by default
- Installation, client compatibility and comprehensive security have not been independently audited. Authentication and access depend on the configured services.
- A project-specific SECURITY.md policy was not available at the fetched official path; the review remains limited to published repository notices.
- No installation, runtime, client matrix, or complete tool-contract audit was performed in this review.
- The fetched official SECURITY.md path returned HTTP 404; it was not treated as positive evidence.
- The workflow requires a public tunnel component.
- The bridge intentionally omits write, shell and commit tools.
Original activity observations
- 2026-10-01T05:14:35Z: docs: honor CODEX HOME in Codex paths ( 443)
Technical identity
github.com/xiaoduoya/codex-with-chatgpt- Exact implementation source
- https://github.com/xiaoduoya/codex-with-chatgpt ↗
- Reviewed resource type
- Gateway
- Repository identity
- XiaoDuoYa/codex-with-chatgpt
Evidence & Sources
- Evidence basis
- Recorded source evidence
- Setup runtime verification
- Not independently runtime-tested by MCP100 for this setup workflow.
Reviewed · Latest source observation
- GitHub repository ↗
xiaoduoya/codex-with-chatgpt
Recorded repository material and project history.
Includes references whose attribution is not established.
Setup · Watchlist
Self-hosted gateway service setup
Publisher instructions.
Source evidence observed .
Additional setup details required — see the specific gaps below.
Install / connect
Publisher instructionsBuild repo, install Codex skill, and perform `c2c setup` OAuth pairing. This is a Codex skill + ChatGPT connector, not a generic mcpServers plugin.
Configure / authenticate
MCP100 setup guidePublisher Codex+ChatGPT integration: git clone exact repo, ensure Node >=20 and Git, run `corepack pnpm install` + `corepack pnpm build`, place its Codex skill under CODEX_HOME and complete documented c2c setup. It is not a generic MCP server package.
Previously reviewed prerequisites / client guidance: install `skill/` into <CODEX_HOME>/skills/codex-with-chatgpt (fallback ~/.codex/skills/codex-with-chatgpt)
Previously reviewed prerequisites / client guidance: Setup may introduce a tunnel, inspect permissions and access before connecting.
Check connection
Suggested checkCheck the installed Codex skill is discovered and its bridge setup reports connected; do not test by uploading private repositories.
Remove / uninstall / revoke
Suggested checkRemove the installed Codex skill from the appropriate CODEX_HOME skills folder and the project's specific MCP bridge registration, if installed; remove the checkout only after checking config references. This is a Codex+ChatGPT integration, not a generic MCP server package.
Client unregistration, program uninstall, persistent-data deletion, and credential revocation must be treated separately.
What it does
Codex with ChatGPT is a read-only MCP bridge that lets ChatGPT plan and review coding work while Codex performs execution in the workspace.
- Capability
- AI & Reasoning
- Resource type
- Gateway
- Industry
- Software & Technology
- Best fit
- Pairing ChatGPT planning/review with Codex coding execution through a read-only workspace bridge.
Representative uses
- Review selected workspace lines
- Plan coding changes with ChatGPT
- Keep execution in Codex
- Expose a workspace through a protected tunnel
Limitations
- The workflow requires a public tunnel component.
- The bridge intentionally omits write, shell and commit tools.
Reviewed access
Access & risk
Review the exact access boundary before connecting this MCP to accounts, credentials, or sensitive data.
- Authentication
- OAuth 2.1 with PKCE S256 and one-time pairing code.
- Permissions
- Read-only workspace-bound access.
- Data handling
- Repository content stays in the workspace; the project documents default denial for sensitive files.
- Cost
- free
- Risk and cautions
- The bridge is intentionally read-only and documents workspace scoping, sensitive-file denial and OAuth protection.
Access scope and cautions
- Write actions
- None in the reviewed inventory
- Sensitive access
- Selected source files; sensitive credential paths are denied by default
- Risk level
- low
- Security notes
- No write/delete/shell/commit tools are exposed by design.
FAQ
Based on reviewed evidence as of 2026-10-06. Watchlist tracking is not a recommendation or a security certification.
Which tasks are documented for this implementation?
What authentication is documented?
Can it modify data or perform write operations?
What data-handling boundary should I consider?
What limitations and risks should I check before use?
Is this an official MCP?
XiaoDuoYa is listed as Community implementation in MCP100’s current evidence.